Description
In this episode, our guest is Ben Recht. Ben is a Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. We discuss several topics, including his research trajectory, Ben's tour of reinforcement learning, and his passion for music, among others. Check out Ben's website here: http://people.eecs.berkeley.edu/~brecht/
Outline
00:00 - Intro
01:01 - Ben predicts the birth of "inControl"
02:40 - Personal research trajectory
06:55 - How and why did you dive into control theory?
08:43 - Influential figures who shaped Ben's research
13:50 - The "argmin" blog & myth busting
27:43 - Ben's tour of reinforcement learning
45:18 - Future challenges for control
52:06 - Biological origin of learning
58:24 - "This or that" game
1:02:54 - Questions from the audience
1:14:51 - What would you do if you were a student today?
1:17:00 - Ben's band: "the fun years"
Episode links
Ben's website: http://people.eecs.berkeley.edu/~brecht/
argmin: http://www.argmin.net/
the fun years: http://thefunyears.com/
A tour of reinforcement learning: https://arxiv.org/abs/1806.09460
Patterns, predictions and actions: http://mlstory.org/
System level synthesis: https://arxiv.org/abs/1904.01634
Aizerman's conjecture: https://en.wikipedia.org/wiki/Aizerman%27s_conjecture
Podcast info
Podcast website: https://www.incontrolpodcast.com/
Apple Podcasts: https://podcasts.apple.com/us/podcast/incontrol/id1624068002
Spotify: https://open.spotify.com/show/7dZvt77XNtHxyrFqM8YTwf
RSS: https://feeds.buzzsprout.com/1632769.rss
Youtube: https://www.youtube.com/channel/UCl83hwBSVRLYj2NWS08P9bg/featured
Facebook: https://www.facebook.com/InControl-podcast-114303337936834
Twitter: https://twitter.com/IncontrolP
Instagram: https://www.instagram.com/incontrol_podcast/
Patreon: https://www.patreon.com/incontrolpodcast/
Acknowledgments and sponsors
This episode was supported by the National Centre of Competence in Research on «Dependable, ubiquitous automation», which you can check here:
https://nccr-automation.ch/nccr-automation
The podcast benefits from the help of an incredibly talented and passionate team. Special thanks to Arian Bastani, Benjamin Sawicki, Elise Cahard, Florian Dorfler, Frederik Banis, John Lygeros, ETH studio (Philipp Zumbrunnen), and mirrorlake studio (Roman Frischknecht). The support of the Swiss National Science Foundation is also gratefully acknowledged.
Music was composed by A New Element.
Support the show
Outline00:00 - Intro02:14 - Early steps in control05:36 - L1 control17:09 - Relay feedback systems24:32 - Agile robotic maneuvers29:31 - Abstractions and models41:59 - Causality49:35 - Markets and power grids1:00:20 - Role of network structure1:05:03 - Data, systems, and society1:16:17 - On...
Published 10/17/24
Outline00:00 - Intro00:49 - Early education and PhD in control10:35 - Non-negative linear algebra & modelling uncertainty principle22:50 - Influence of Willems & the Frisch scheme34:27 - Subspace identification & stochastic behavioural system theory38:39 - Stanford experience with...
Published 08/21/24